[cleanup] Misc (#8338)

Authored by: bashonly, gamer191

README.md

@@ -89,7 +89,6 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
     * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326) **\***
     * Supports some (but not all) age-gated content without cookies
     * Download livestreams from the start using `--live-from-start` (*experimental*)
-    * `255kbps` audio is extracted (if available) from YouTube Music when premium cookies are given
     * Channel URLs download all uploads of the channel, including shorts and live
 
 * **Cookies from browser**: Cookies can be automatically extracted from all major web browsers using `--cookies-from-browser BROWSER[+KEYRING][:PROFILE][::CONTAINER]`
@@ -913,7 +912,7 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     Defaults to ~/.netrc
     --netrc-cmd NETRC_CMD           Command to execute to get the credentials
                                     for an extractor.
-    --video-password PASSWORD       Video password (vimeo, youku)
+    --video-password PASSWORD       Video-specific password
     --ap-mso MSO                    Adobe Pass multiple-system operator (TV
                                     provider) identifier, use --ap-list-mso for
                                     a list of available MSOs

yt_dlp/extractor/banbye.py

@@ -31,7 +31,7 @@ class BanByeBaseIE(InfoExtractor):
 
 
 class BanByeIE(BanByeBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?watch/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?watch/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://banbye.com/watch/v_ytfmvkVYLE8T',
         'md5': '2f4ea15c5ca259a73d909b2cfd558eb5',
@@ -120,7 +120,7 @@ class BanByeIE(BanByeBaseIE):
 
 
 class BanByeChannelIE(BanByeBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?banbye.com/(?:en/)?channel/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?banbye\.com/(?:en/)?channel/(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://banbye.com/channel/ch_wrealu24',
         'info_dict': {

yt_dlp/extractor/breitbart.py

@@ -2,7 +2,7 @@ from .common import InfoExtractor
 
 
 class BreitBartIE(InfoExtractor):
-    _VALID_URL = r'https?:\/\/(?:www\.)breitbart.com/videos/v/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?breitbart\.com/videos/v/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.breitbart.com/videos/v/5cOz1yup/?pl=Ij6NDOji',
         'md5': '0aa6d1d6e183ac5ca09207fe49f17ade',

yt_dlp/extractor/craftsy.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class CraftsyIE(InfoExtractor):
-    _VALID_URL = r'https?://www.craftsy.com/class/(?P<id>[a-z0-9_-]+)/'
+    _VALID_URL = r'https?://www\.craftsy\.com/class/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://www.craftsy.com/class/the-midnight-quilt-show-season-5/',
         'info_dict': {

yt_dlp/extractor/cybrary.py

@@ -45,7 +45,7 @@ class CybraryBaseIE(InfoExtractor):
 
 
 class CybraryIE(CybraryBaseIE):
-    _VALID_URL = r'https?://app.cybrary.it/immersive/(?P<enrollment>[0-9]+)/activity/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://app\.cybrary\.it/immersive/(?P<enrollment>[0-9]+)/activity/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://app.cybrary.it/immersive/12487950/activity/63102',
         'md5': '9ae12d37e555cb2ed554223a71a701d0',
@@ -110,7 +110,7 @@ class CybraryIE(CybraryBaseIE):
 
 
 class CybraryCourseIE(CybraryBaseIE):
-    _VALID_URL = r'https://app.cybrary.it/browse/course/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'https://app\.cybrary\.it/browse/course/(?P<id>[\w-]+)/?(?:$|[#?])'
     _TESTS = [{
         'url': 'https://app.cybrary.it/browse/course/az-500-microsoft-azure-security-technologies',
         'info_dict': {

yt_dlp/extractor/fifa.py

@@ -8,7 +8,7 @@ from ..utils import (
 
 
 class FifaIE(InfoExtractor):
-    _VALID_URL = r'https?://www.fifa.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
+    _VALID_URL = r'https?://www\.fifa\.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
         'info_dict': {

yt_dlp/extractor/filmmodu.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none
 
 
 class FilmmoduIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?filmmodu.org/(?P<id>[^/]+-(?:turkce-dublaj-izle|altyazili-izle))'
+    _VALID_URL = r'https?://(?:www\.)?filmmodu\.org/(?P<id>[^/]+-(?:turkce-dublaj-izle|altyazili-izle))'
     _TESTS = [{
         'url': 'https://www.filmmodu.org/f9-altyazili-izle',
         'md5': 'aeefd955c2a508a5bdaa3bcec8eeb0d4',

yt_dlp/extractor/itprotv.py

@@ -31,7 +31,7 @@ class ITProTVBaseIE(InfoExtractor):
 
 
 class ITProTVIE(ITProTVBaseIE):
-    _VALID_URL = r'https://app.itpro.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
+    _VALID_URL = r'https://app\.itpro\.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://app.itpro.tv/course/guided-tour/introductionitprotv',
         'md5': 'bca4a28c2667fd1a63052e71a94bb88c',
@@ -102,7 +102,7 @@ class ITProTVIE(ITProTVBaseIE):
 
 
 class ITProTVCourseIE(ITProTVBaseIE):
-    _VALID_URL = r'https?://app.itpro.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
     _TESTS = [
         {
             'url': 'https://app.itpro.tv/course/guided-tour',

yt_dlp/extractor/jable.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class JableIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jable.tv/videos/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://jable.tv/videos/pppd-812/',
         'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
@@ -64,7 +64,7 @@ class JableIE(InfoExtractor):
 
 
 class JablePlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?jable.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://jable.tv/models/kaede-karen/',
         'info_dict': {

yt_dlp/extractor/kommunetv.py

@@ -3,7 +3,7 @@ from ..utils import update_url
 
 
 class KommunetvIE(InfoExtractor):
-    _VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
+    _VALID_URL = r'https://\w+\.kommunetv\.no/archive/(?P<id>\w+)'
     _TEST = {
         'url': 'https://oslo.kommunetv.no/archive/921',
         'md5': '5f102be308ee759be1e12b63d5da4bbc',

yt_dlp/extractor/mainstreaming.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 
 class MainStreamingIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:webtools-?)?(?P<host>[A-Za-z0-9-]*\.msvdn\.net)/(?:embed|amp_embed|content)/(?P<id>\w+)'
     _EMBED_REGEX = [rf'<iframe[^>]+?src=["\']?(?P<url>{_VALID_URL})["\']?']
     IE_DESC = 'MainStreaming Player'
 

yt_dlp/extractor/mediaite.py

@@ -2,7 +2,7 @@ from .common import InfoExtractor
 
 
 class MediaiteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?mediaite.com(?!/category)(?:/[\w-]+){2}'
+    _VALID_URL = r'https?://(?:www\.)?mediaite\.com(?!/category)(?:/[\w-]+){2}'
     _TESTS = [{
         'url': 'https://www.mediaite.com/sports/bill-burr-roasts-nfl-for-promoting-black-lives-matter-while-scheduling-more-games-after-all-the-sht-they-know-about-cte/',
         'info_dict': {

yt_dlp/extractor/mocha.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none, traverse_obj
 
 
 class MochaVideoIE(InfoExtractor):
-    _VALID_URL = r'https?://video.mocha.com.vn/(?P<video_slug>[\w-]+)'
+    _VALID_URL = r'https?://video\.mocha\.com\.vn/(?P<video_slug>[\w-]+)'
     _TESTS = [{
         'url': 'http://video.mocha.com.vn/chuyen-meo-gia-su-tu-thong-diep-cuoc-song-v18694039',
         'info_dict': {

yt_dlp/extractor/nfl.py

@@ -247,7 +247,7 @@ class NFLArticleIE(NFLBaseIE):
 
 class NFLPlusReplayIE(NFLBaseIE):
     IE_NAME = 'nfl.com:plus:replay'
-    _VALID_URL = r'https?://(?:www\.)?nfl.com/plus/games/(?P<slug>[\w-]+)(?:/(?P<id>\d+))?'
+    _VALID_URL = r'https?://(?:www\.)?nfl\.com/plus/games/(?P<slug>[\w-]+)(?:/(?P<id>\d+))?'
     _TESTS = [{
         'url': 'https://www.nfl.com/plus/games/giants-at-vikings-2022-post-1/1572108',
         'info_dict': {
@@ -342,7 +342,7 @@ class NFLPlusReplayIE(NFLBaseIE):
 
 class NFLPlusEpisodeIE(NFLBaseIE):
     IE_NAME = 'nfl.com:plus:episode'
-    _VALID_URL = r'https?://(?:www\.)?nfl.com/plus/episodes/(?P<id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?nfl\.com/plus/episodes/(?P<id>[\w-]+)'
     _TESTS = [{
         'note': 'Subscription required',
         'url': 'https://www.nfl.com/plus/episodes/kurt-s-qb-insider-conference-championships',

yt_dlp/extractor/novaplay.py

@@ -3,7 +3,7 @@ from ..utils import int_or_none, parse_duration, parse_iso8601
 
 
 class NovaPlayIE(InfoExtractor):
-    _VALID_URL = r'https://play.nova\.bg/video/.*/(?P<id>\d+)'
+    _VALID_URL = r'https://play\.nova\.bg/video/[^?#]+/(?P<id>\d+)'
     _TESTS = [
         {
             'url': 'https://play.nova.bg/video/ochakvaite/season-0/ochakvaite-2022-07-22-sybudi-se-sat/606627',

yt_dlp/extractor/nubilesporn.py

@@ -19,7 +19,7 @@ from ..utils import (
 class NubilesPornIE(InfoExtractor):
     _NETRC_MACHINE = 'nubiles-porn'
     _VALID_URL = r'''(?x)
-        https://members.nubiles-porn.com/video/watch/(?P<id>\d+)
+        https://members\.nubiles-porn\.com/video/watch/(?P<id>\d+)
         (?:/(?P<display_id>[\w\-]+-s(?P<season>\d+)e(?P<episode>\d+)))?
     '''
 

yt_dlp/extractor/oftv.py

@@ -4,7 +4,7 @@ from ..utils import traverse_obj
 
 
 class OfTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?of.tv/video/(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?of\.tv/video/(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://of.tv/video/627d7d95b353db0001dadd1a',
         'md5': 'cb9cd5db3bb9ee0d32bfd7e373d6ef0a',
@@ -34,7 +34,7 @@ class OfTVIE(InfoExtractor):
 
 
 class OfTVPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?of.tv/creators/(?P<id>[a-zA-Z0-9-]+)/.?'
+    _VALID_URL = r'https?://(?:www\.)?of\.tv/creators/(?P<id>[a-zA-Z0-9-]+)/?(?:$|[?#])'
     _TESTS = [{
         'url': 'https://of.tv/creators/this-is-fire/',
         'playlist_count': 8,

yt_dlp/extractor/sina.py

@@ -11,7 +11,7 @@ from ..utils import (
 
 
 class SinaIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:.*?\.)?video\.sina\.com\.cn/
+    _VALID_URL = r'''(?x)https?://(?:[^/?#]+\.)?video\.sina\.com\.cn/
                         (?:
                             (?:view/|.*\#)(?P<id>\d+)|
                             .+?/(?P<pseudo_id>[^/?#]+)(?:\.s?html)|

yt_dlp/extractor/twitter.py

@@ -1741,7 +1741,7 @@ class TwitterSpacesIE(TwitterBaseIE):
 
 class TwitterShortenerIE(TwitterBaseIE):
     IE_NAME = 'twitter:shortener'
-    _VALID_URL = r'https?://t.co/(?P<id>[^?]+)|tco:(?P<eid>[^?]+)'
+    _VALID_URL = r'https?://t\.co/(?P<id>[^?#]+)|tco:(?P<eid>[^?#]+)'
     _BASE_URL = 'https://t.co/'
 
     def _real_extract(self, url):

yt_dlp/extractor/utreon.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class UtreonIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?utreon.com/v/(?P<id>[a-zA-Z0-9_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?utreon\.com/v/(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://utreon.com/v/z_I7ikQbuDw',
         'info_dict': {

yt_dlp/extractor/vk.py

@@ -97,12 +97,12 @@ class VKIE(VKBaseIE):
                         (?:
                             (?:
                                 (?:(?:m|new)\.)?vk\.com/video_|
-                                (?:www\.)?daxab.com/
+                                (?:www\.)?daxab\.com/
                             )
                             ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
                             (?:
                                 (?:(?:m|new)\.)?vk\.com/(?:.+?\?.*?z=)?(?:video|clip)|
-                                (?:www\.)?daxab.com/embed/
+                                (?:www\.)?daxab\.com/embed/
                             )
                             (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
                         )

yt_dlp/extractor/weverse.py

@@ -182,7 +182,7 @@ class WeverseBaseIE(InfoExtractor):
 
 
 class WeverseIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/live/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/live/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/live/0-107323480',
         'md5': '1fa849f00181eef9100d3c8254c47979',
@@ -344,7 +344,7 @@ class WeverseIE(WeverseBaseIE):
 
 
 class WeverseMediaIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/media/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/media/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/media/4-116372884',
         'md5': '8efc9cfd61b2f25209eb1a5326314d28',
@@ -420,7 +420,7 @@ class WeverseMediaIE(WeverseBaseIE):
 
 
 class WeverseMomentIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<artist>[^/?#]+)/moment/(?P<uid>[\da-f]+)/post/(?P<id>[\d-]+)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<artist>[^/?#]+)/moment/(?P<uid>[\da-f]+)/post/(?P<id>[\d-]+)'
     _TESTS = [{
         'url': 'https://weverse.io/secretnumber/moment/66a07e164b56a696ee71c99315ffe27b/post/1-117229444',
         'md5': '87733ac19a54081b7dfc2442036d282b',
@@ -516,7 +516,7 @@ class WeverseTabBaseIE(WeverseBaseIE):
 
 
 class WeverseLiveTabIE(WeverseTabBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/live/?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/live/?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/live/',
         'playlist_mincount': 55,
@@ -534,7 +534,7 @@ class WeverseLiveTabIE(WeverseTabBaseIE):
 
 
 class WeverseMediaTabIE(WeverseTabBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/media(?:/|/all|/new)?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/media(?:/|/all|/new)?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/billlie/media/',
         'playlist_mincount': 231,
@@ -558,7 +558,7 @@ class WeverseMediaTabIE(WeverseTabBaseIE):
 
 
 class WeverseLiveIE(WeverseBaseIE):
-    _VALID_URL = r'https?://(?:www\.|m\.)?weverse.io/(?P<id>[^/?#]+)/?(?:[?#]|$)'
+    _VALID_URL = r'https?://(?:www\.|m\.)?weverse\.io/(?P<id>[^/?#]+)/?(?:[?#]|$)'
     _TESTS = [{
         'url': 'https://weverse.io/purplekiss',
         'info_dict': {

yt_dlp/extractor/wimtv.py

@@ -11,7 +11,7 @@ class WimTVIE(InfoExtractor):
     _player = None
     _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
     _VALID_URL = r'''(?x:
-        https?://platform.wim.tv/
+        https?://platform\.wim\.tv/
         (?:
             (?:embed/)?\?
             |\#/webtv/.+?/

yt_dlp/extractor/xhamster.py

@@ -24,7 +24,7 @@ class XHamsterIE(InfoExtractor):
     _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:.+?\.)?%s/
+                        (?:[^/?#]+\.)?%s/
                         (?:
                             movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
                             videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
@@ -372,7 +372,7 @@ class XHamsterIE(InfoExtractor):
 
 
 class XHamsterEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
+    _VALID_URL = r'https?://(?:[^/?#]+\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
     _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1']
     _TEST = {
         'url': 'http://xhamster.com/xembed.php?video=3328539',

yt_dlp/extractor/youtube.py

@@ -949,7 +949,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         main_rm = next(main_retries)
         # Manual retry loop for multiple RetryManagers
         # The proper RetryManager MUST be advanced after an error
-        # and it's result MUST be checked if the manager is non fatal
+        # and its result MUST be checked if the manager is non fatal
         while True:
             try:
                 response = self._call_api(

yt_dlp/extractor/zoom.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class ZoomIE(InfoExtractor):
     IE_NAME = 'zoom'
-    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?P<type>play|share)/(?P<id>[A-Za-z0-9_.-]+)'
+    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom\.us/)rec(?:ording)?/(?P<type>play|share)/(?P<id>[\w.-]+)'
     _TESTS = [{
         'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
         'md5': 'ab445e8c911fddc4f9adc842c2c5d434',

yt_dlp/options.py

@@ -727,7 +727,7 @@ def create_parser():
     authentication.add_option(
         '--video-password',
         dest='videopassword', metavar='PASSWORD',
-        help='Video password (vimeo, youku)')
+        help='Video-specific password')
     authentication.add_option(
         '--ap-mso',
         dest='ap_mso', metavar='MSO',